Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    true/false configuration values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     एकदम
    0.39
    pi
    0.38
    quality
    0.38
     maximal
    0.38
    maxim
    0.37
     precision
    0.37
    ~.,
    0.37
    "))
    0.36
    صح
    0.36
    apse
    0.36
    POSITIVE LOGITS
     ফ্লাই
    0.41
    ргани
    0.40
    গুলির
    0.38
     автомобі
    0.37
     ٹ
    0.37
    сида
    0.36
     వెం
    0.36
     सोसायटी
    0.36
     CLIN
    0.36
     NIE
    0.36
    Act Density 0.001%

    No Known Activations